Hormuz Strait Monitor

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:37 PM UTC
• Version:
  1.0.0

Overview

This skill appears to do what it says: it opens two public shipping websites, records transit metrics locally, and has normal browser-automation dependency risks.

Install only if you are comfortable running Chrome/Selenium automation and allowing webdriver-manager to download ChromeDriver. Expect local CSV history and possible debug files under ~/.openclaw/workspace/memory, and review any future real notification integration before enabling external channels.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (3)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 94% confidence
• Finding: The skill documentation shows operational capabilities to invoke Python, access workspace paths, and write persistent output files, yet no permissions are declared. This creates a transparency and governance gap: a user or platform may authorize or run the skill without realizing it can read local files, write data to persistent storage, and execute shell-level commands, increasing the risk of unintended data exposure or misuse.

Context-Inappropriate Capability

Medium

• Confidence: 88% confidence
• Finding: The script downloads and executes a ChromeDriver binary at runtime from an external source, which introduces a software supply-chain and unreviewed code-execution path unrelated to the core monitoring logic. In a security-sensitive agent environment, this increases risk because remote binary retrieval can be tampered with, blocked, or yield unexpected versions with elevated execution impact.

Missing User Warnings

Low

• Confidence: 88% confidence
• Finding: The skill persists collected monitoring data and alert information to a CSV in workspace memory, but the description does not prominently warn users about this retention behavior. While the stored data appears operational rather than highly sensitive, undisclosed persistence can still surprise users, create unnecessary retention, and expose historical monitoring data to other workspace processes or users.

VirusTotal

63/63 vendors flagged this skill as clean.